US20060190656A1 - Flexible processing hardware architecture - Google Patents
Flexible processing hardware architecture Download PDFInfo
- Publication number
- US20060190656A1 US20060190656A1 US11/404,193 US40419306A US2006190656A1 US 20060190656 A1 US20060190656 A1 US 20060190656A1 US 40419306 A US40419306 A US 40419306A US 2006190656 A1 US2006190656 A1 US 2006190656A1
- Authority
- US
- United States
- Prior art keywords
- pci
- bus
- vision processing
- subsystem
- host
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
- 238000012545 processing Methods 0.000 title claims abstract description 88
- 230000002093 peripheral effect Effects 0.000 claims abstract description 36
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000008878 coupling Effects 0.000 claims 1
- 238000010168 coupling process Methods 0.000 claims 1
- 238000005859 coupling reaction Methods 0.000 claims 1
- 230000015654 memory Effects 0.000 abstract description 56
- 238000000034 method Methods 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 125000000524 functional group Chemical group 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/40—Bus structure
- G06F13/4004—Coupling between buses
- G06F13/4027—Coupling between buses using bus bridges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/60—Memory management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
Definitions
- This invention relates to the field of flexible and modifiable processing hardware architecture and more particularly, to a processing hardware architecture that allows for multiple system configurations.
- PC personal computer
- a frame grabber or camera interface board or system resides on the PC's peripheral bus and is used to acquire images from one or more cameras into the PC's memory where the images can be accessed and processed by the PC CPU.
- This will be referred to as the frame grabber or host processing configuration since the host CPU is solely responsible for all image processing operations.
- Another class of such systems uses a plug-in processor accelerator board to assist the PC CPU in performing some of the computationally expensive and extensive image processing operations. This will be referred to as the vision accelerator or accelerated host processing configuration.
- Yet another possible configuration involves a complete image processing or machine vision subsystem in the form of an expansion board plugged in the PC's peripheral bus.
- This board features and on-board CPU, often also coupled with dedicated image processing acceleration hardware.
- the embedded or target CPU completely off-loads all vision processing operations from the host PC CPU which can now be dedicated to user interface, control, or other tasks running on it concurrently with the image/vision processing tasks running on the vision processor.
- This multiprocessing configuration will be referred to as the embedded vision processing engine or target processing configuration.
- a final configuration uses the PC only as the programming and/or user interface environment for a standalone vision processing engine connected to it through a high speed serial or network connection. This configuration will be referred to as the standalone vision processing engine or standalone target processing configuration.
- the PCI bus 1 has enabled high bandwidth data transfers between a plug-in device such as an image acquisition or image processing board and the host PC, further enhancing the performance of all the above mentioned embedded system configurations.
- a plug-in device such as an image acquisition or image processing board
- the host PC further enhancing the performance of all the above mentioned embedded system configurations.
- PCI bus As a local bus is not without its drawbacks however.
- the PCI bus was designed primarily for the PC market and as such, the topology and data flow is directed from a host CPU through a host bus bridge to a tree of peripheral buses connected through PCI to PCI bridges (herein referred to as peripheral bridges).
- the host CPU expects to be the only CPU in the system and also expects that its main memory is fixed in the system memory map. Any plug-in card, board or device with an embedded CPU has to allow its local memory to be mapped to avoid conflict with the host PC memory.
- Memory assignments may come from one or two sources: PCI BIOS or the host operating system (OS). Care must be taken when necessary to avoid system lockups by either hiding devices behind the peripheral bus bridges (where they are inaccessible by the host PC system), or by temporarily disconnecting them from the PCI bus until they are ready to accept bus transactions.
- a further drawback to using the PCI bus as a local bus inside PCI based systems is caused by a video graphics adapter (VGA), herein referred to as the display controller, and the discovery process used by the PCI BIOS and host Operating System (OS) to determine the system display controller.
- VGA video graphics adapter
- OS operating System
- PCI BIOS manufacturers using different discovery algorithms some of which become confused by more than one display controller on the PCI bus.
- PCI adapter card manufacturers who write drivers for their products sometimes introduce problems, e.g. when an expansion card has a peripheral bridge chip.
- a flexible vision processing architecture that uses the PCI bus as the embedded processor local bus and which enables a variety of embedded and standalone vision system configurations to be implemented with either no or only minor hardware and software modifications.
- the reconfigurable processing system architecture allows for the implementation of a variety of vision or other system configurations to be implemented on a single device, which, in one embodiment, is preferably a PCI bus add-in extension board with an attached digitizer daughter card attached and electrically connected thereto through a PCI Mezzanine connector, and which is plugged into a personal computer PCI expansion slot.
- the flexible and reconfigurable processing hardware architecture of the present invention uses the PCI bus as the embedded vision processor CPU's local bus, which not only allows for flexibility in vision system configuration but also allows PCI devices to be hidden from the host CPU to allow for proper system startup.
- the architecture further permits an embedded vision processing CPU to be re-booted when the secondary PCI bus host bus bridge fails to respond without affecting host CPU or other secondary PCI bus peripheral devices.
- the architecture of the present invention provides a method of loading an embedded vision system CPU's local memory with operating system and diagnostic code without the use of ROM or FLASH memory.
- FIG. 1 is a the block diagram of an embedded processing engine configuration
- FIG. 2 is a block diagram of a processing accelerator (with digitizer) configuration according to one embodiment of the present invention
- FIG. 3 is a block diagram of a processing accelerator configured without a digitizer, according to another embodiment of the invention.
- FIG. 4 is a block diagram of a frame grabber configuration according to yet another embodiment of the invention.
- FIG. 5 is a block diagram of a standalone vision processing engine architecture according to one embodiment of the present invention.
- FIG. 6 is a schematic diagram showing a summary of some of the various different architectural configurations from the previous Figures;
- FIG. 7 is a flow chart showing the steps to accomplish the boot time reset.
- FIG. 8 is a schematic diagram of a system for implementing the bus memory reservation according to another feature of the present invention.
- the hardware described in this invention comprises, in the preferred embodiment, a PCI bus add-in extension board 100 that includes a digitizer subsystem D embodied, for exemplary purposes, in a digitizer daughter card attached and electrically connected to extension board 100 through a PCI Mezzanine connector 2 (pmc) 36 ; although such an implementation is not a limitation of the present invention.
- PCI Mezzanine connector 2 (pmc) 36 ; although such an implementation is not a limitation of the present invention. 2 Draft Standard Physical and Environmental Layers for PCI Mezzanine Cards: PMC, IEEE 1386/Draft 2.0, Apr. 4, 1995
- the present invention will be explained utilizing the PCI bus for exemplary purposes, this is not a limitation of the present invention.
- the compact PCI bus specification which in one implementation is a 64 bit bus operating at 66 MHz and any other PCI bus specification to be specified in the future are considered to be within the scope of the present invention.
- any flexible architecture which utilizes a bus structure which makes two (2) devices look like they are connected together including a bus which allows for bus extensions with or without electrical buffering, and which bus and bus extension are designed to operate as a single bus, is considered to be within the scope of the present invention.
- PCI to PCI bridge 3 25 which interfaces a host CPU PCI peripheral bus 27 to a secondary, vision processing system PCI bus 26 included on the PCI extension board.
- the extension board 100 also includes a processing accelerator subsystem A, implemented preferably as an ASIC (application specific integrated circuit) 20 , a VGA (video graphics adapter) or similar display controller 33 , and a system CPU subsystem C.
- the components of the system CPU subsystem C include an embedded system CPU 16 , which interfaces to the host system PCI bus 27 via a CPU subsystem CPU bus 15 , a host bus bridge 17 , and the PCI to PCI bridge 25 .
- Host system components which may be included in the subsystem include local DRAM (dynamic random access memory) system memory 22 and system peripherals 21 such as a DUART RS232 serial controller, NVRAM (non-volatile random access memory) with a real-time clock and a CPLD (complex programmable logic device) providing registers, CPU startup information and other board “glue” logic, as is well known in the art. Power is continually monitored by a CPU supervisory chip, which provides advanced warning to the CPU in the event of a power failure and further provides for manual board reset.
- DRAM dynamic random access memory
- NVRAM non-volatile random access memory
- CPLD complex programmable logic device
- digitized video data is sent from the digitizer 12 (a true data digitizer 12 in the case of an analog camera 14 , or a camera interface 12 if the camera 14 is a digital camera) or other general purpose interface over the secondary, vision system PCI bus 26 to local DRAM 22 on the board or to the host PC's local display controller 35 having its own memory 37 .
- the vision processing accelerator 20 “snoops” these transactions using snoop handshake, 21 , thus loading the ASIC memory 18 a and 18 b with the digitized video information.
- the data is sent to the embedded vision system CPU 16 for further processing.
- the data may be displayed on local display 28 from the local display controller 33 or as an overlay in the host PC's display controller.
- a plurality of boards can be mapped anywhere into PC memory within the host PC resource constraints and will not cause boot time conflicts with the PC hardware.
- the present invention includes the disclosed architecture which allows a wide variety of system variants to be implemented with minimal hardware and software incremental investment.
- FIG. 1 shows the basic configuration for a vision processing engine system embedded in a PC as a PCI expansion board.
- the present invention takes advantage of widely available components and easily implements alternative vision system configurations through different combinations of the major functional groupings of the base architecture as will be explained below.
- the main such functional groups shown in FIG. 1 are the digitizer (also referred to as the frame grabber or camera interface) subsystem D, the vision CPU subsystem C, and the vision accelerator subsystem A. All these subsystems are connected to each other through the secondary, vision processing system PCI bus 26 which is itself connected to the PC's (Host CPU) PCI bus 27 , host CPU 24 and associated memory 32 through a bus peripheral bus interface, which, in this embodiment is a PCI-to-PCI bus bridge 25 3 . 3 PCI to PCI Bridge Architecture Specification, Rev. 1.0, Apr. 5, 1994.
- image data 13 from multiple cameras 14 a - 14 d can be processed by the vision accelerator 20 , the embedded vision system CPU 16 , or by a host CPU 24 in cases where the vision system is resident on the host CPU peripheral data bus (e.g. as an adapter or peripheral card).
- a vision system often includes a local display 28 and serial and discrete input/output ports 30 to support real-time machine vision operations and intercommunications with other devices.
- the digitizer 12 in this implementation packs multiple pixels (data samples) into a larger word to match the width of the vision processing system PCI bus 26 . If the memory data bus 19 width and the vision processing system PCI bus 26 width are not the same, the processing accelerator 20 would reformat peripheral bus words to match the width of the memory data bus 19 or the vision processing system PCI bus 26 .
- the digitizer 12 in connection with direct memory access (DMA) master controller 7 , moves pixel data samples in high speed bursts into a portion of peripheral data bus address space.
- this may be one of the image memories 18 a and/or 18 b , shared vision system CPU memory 22 , host CPU memory 32 , display controller memory 34 , or host display controller memory 37 .
- the digitizer subsystem D is implemented as a mezzanine daughter card.
- a variety of different camera interface boards can be combined with the same vision processing engine board 100 .
- the connection to such a mezzanine card is through a PCI mezzanine connector (PMC) 36 .
- FIG. 2 shows a cost reduced version of the embedded vision engine configuration of FIG. 1 wherein the embedded vision system CPU 16 , host bus bridge 17 , system memory 22 , system peripherals 26 b and display controller are removed to create the accelerated host configuration mentioned earlier.
- the vision processing system comprises a digitizer subsystem D, which includes substantially the same components discussed above with respect to the-digitizer subsystem of FIG. 1 .
- the common components of the two digitizer subsystems are identified using the same reference numerals.
- the second component of the vision processing system of FIG. 2 is the vision accelerator subsystem A, which, like the digitizer subsystem D, is substantially identical to the processing accelerator subsystem A of FIG. 1 and common components are indicated using the same reference numerals.
- This embodiment can be implemented using a plug-in expansion card in much the same manner as the embodiment of FIG. 1 . However, the expansion card would not include the components of the vision CPU subsystem C (of FIG. 1 ).
- the, host CPU 24 is tasked with running the vision subsystem application.
- the vision accelerator subsystem would still be available with its processing accelerator ASIC 20 , which would allow digitized video information to be pre-processed before it is routed to the host CPU 24 for further processing.
- FIG. 3 shows a further cost-reduced variation of the above-mentioned processing accelerator configuration.
- This configuration incorporates only the processing accelerator subsystem A without a digitizer subsystem.
- images are acquired through a separate frame grabber board (not shown).
- the host PC CPU 24 runs the vision application.
- the vision processing accelerator ASIC 20 is still available to accelerate vision computations.
- a frame grabber (digitizer) D′ which can be built from the mezzanine card components by changing the PCI mezzanine connector ( 36 of FIG. 1 ) to a standard PCI edge connector (not shown), may interface directly to the host CPU PCI peripheral bus 27 . This further allows for the development of software drivers from existing software components.
- FIG. 5 a fifth embodiment of the invention is shown.
- an Ethernet controller 25 c or any other communications means such as PPP (TCPIP protocol over a serial line)
- PPP TPIP protocol over a serial line
- the standalone vision processor configuration includes most of the same components described above with respect to the vision system of FIG. 1 .
- FIG. 1 Other configurations can be envisioned with different functional groupings of the basic subsystems highlighted in FIG. 1 , including for example, but not limited to, incorporating a camera in the same package as the vision processing engine to form a “smart camera” configuration.
- FIGS. 6 a - 6 e A summary of the preceding Figures is shown in FIGS. 6 a - 6 e , wherein block ‘C’ represents the Embedded CPU Subsystem including the CPU, host bus bridge, system memory, peripherals, Ethernet controller and display controller; block ‘D’ represents the Digitizer and Field I/O mezzanine card ( 100 d having a PCI or other system bus compatible edge connector 150 such as a PCI mezzanine connector); and block ‘A’ represents the processing accelerator and its captive memories. “H” represents a host computer, which is accessed via an Ethernet or PPP connection.
- Up to 21 PCI devices may be addressed on a PCI bus.
- the bridge architecture specification will allow up to 16 devices to be addressed.
- Secondary bus addressing is implemented by connecting the device IDSEL line to a PCI address line in the range AD [31:16].
- AD [31:11] When a configuration cycle is issued for a device on the same bus as the target, up to 21 devices may be addressed on AD [31:11], the remaining lines being used to identify configuration cycle type, configuration register number and device function number. This means that a device on the secondary bus (side) of the peripheral bus bridge 25 and connected to AD [15:11] is hidden from the primary side of the peripheral bus bridge 25 , but not from the embedded CPU on the secondary PCI bus.
- the display controller that is used as a local (secondary) display device confuses both the PCI BIOS (Basic Input Output System) and the installed host PC's display controller drivers as to which display device should be used as the system display device. Hiding this local display device behind the PCI bridge (by connecting its IDSEL line to a PCI address line in the range AD [15:11]) means that the display device is only addressable for PCI configuration cycles by the embedded CPU.
- PCI BIOS Basic Input Output System
- this method provides a way to initialize a private device behind a peripheral bridge, the device is always visible in the final system memory map if the peripheral bridge's memory window encompasses the device's assigned memory region.
- Another method to hide PCI devices addresses power-on issues (e.g. when the PCI BIOS tries to interrogate the host bus bridge before its initialization sequence is complete it could cause the host PC to “hang” during boot).
- the other clock(s) may be supplied from a source that has a long startup latency for a variety of reasons.
- the device may also require all clocks to be operational before it can reset its internal state machines. If this delay time is greater than the time that the PC needs before it starts executing its BIOS code, there is the potential for deadlock.
- a state machine (its operation shown in FIG. 7 ) is used to control the reset release and the PCI device's IDSEL connection sequencing, to ensure correct operation—effectively disconnecting the device from the PCI bus until it is ready to accept bus transactions.
- step 110 the state machine 100 asserts cold CPU reset, asserts host bus bridge reset, disables IDSEL to the host bus bridge, asserts warm CPU reset and resets an 8-bit counter to a count value of 0 (counter reset).
- state S 1 step 120 , which is reached when power reaches a sufficient level or manual reset is released, the state machine continues to assert cold CPU reset and host bus bridge reset. It releases the counter reset to allow the counter to increment, and continues to disable IDSEL and assert warm CPU reset.
- step 130 will happen when the counter value reaches 255 (256 clock cycles after S 1 ), and the state machine de-asserts cold CPU reset.
- host bus bridge reset remains asserted as does warm CPU reset.
- IDSEL remains disabled. Thus, the host CPU can load its mode information and start its system clocks.
- step 140 the state machine continues to de-assert cold CPU reset. It also de-asserts host bus bridge reset, thus allowing the bridge to complete its internal initialization. IDSEL remains disabled and warm CPU reset remains asserted.
- step 150 IDSEL is enabled, thus allowing host bus bridge to become visible on the secondary system (vision system in this implementation) and visible to the host PC. (Cold CPU reset and host bus bridge reset remain de-asserted and warm CPU reset remains asserted.)
- State S 4 Progression from state S 4 to state S 5 will generally not occur immediately, the average wait time being 128 clock cycles.
- the 8 bit counter is enabled in all states except state S 0 , and will continually count with a modulo of 256. There is a minimum wait of one cycle possible which is enough to perform a soft reset on the CPU.
- step 160 warm CPU reset is deasserted under software control by deasserting a “halt” register bit with the CPU.
- the embedded (vision) system CPU is allowed to boot. This state progression thus allows two CPU's and multiple, potentially conflicting peripheral components to be sequentially initialized without causing system hang-ups.
- the Boot Time State Machine 100 performs three functions:
- the first feature above solves the problem that the embedded CPU must provide a synchronous clock to the host bus bridge which operates at a different frequency from the oscillator that supplies the embedded CPU. Therefore, the CPU frequency generator must supply the host bus bridge clock. This supplied clock is started only after the embedded CPU has loaded it's mode information from the complex programmable logic device CPLD. Reset must be deasserted only after the clock from the CPU is present so that the host bus bridge can correctly initialize its internal state. PCI accesses should not be responded to until enough PCI clock cycles have passed from reset deassertion to ensure that the reset completes correctly.
- This solution is also equally applicable to a PCI device on the primary or secondary side of a peripheral bridge and anywhere in the PCI bus hierarchy.
- this method provides a way to initialize a private device behind a peripheral bridge, the device is always visible in the final system memory map if the peripheral bridge memory window encompasses the device's assigned memory region.
- the embedded CPU and its devices are inaccessible from the primary PCI bus, including any device registers that can assert a soft reset to the CPU.
- a back-door signal ( 26 d of FIG. 1 ) was created from the peripheral bridge to a system peripheral that ensures resets can be asserted to recover the system. While this is useful primarily for debugging, its use in the driver ensures that no problems occur during driver loading.
- the signal is attached to the peripheral bridge's general purpose input/output (GPIO) port which is addressable from configuration space on the primary bus.
- GPIO general purpose input/output
- An embedded CPU is usually tested and booted by running code that is present in an on-board ROM or FLASH memory because there is no other way to load this code into the embedded CPU's memory.
- code can be loaded over the PCI bus from any source, including an Ethernet device or a host PC.
- any source including an Ethernet device or a host PC.
- This allows the ROM or FLASH memory to be removed from the board which reduces cost and allows easy field updates by disk or Internet/Intranet.
- An additional feature of the present invention facilitates and allows for the use of a non-standard or non-recognized PCI bus connected device such as, for example, a vision system board, embedded CPU or other similar device.
- a non-standard or non-recognized PCI bus connected device such as, for example, a vision system board, embedded CPU or other similar device.
- the main system BIOS the PC (personal computer) boots, the BIOS scans the bus for devices connected to the bus, and allocates system memory for each device. If the BIOS sees a device that it does not recognize, the BIOS ignores the device and does not allocate memory for that particular device.
- the present invention features a system and method for reserving memory in such a situation; such a system and method being completely independent of the type of BIOS and the type of device plugged into the PCI or other bus.
- the system and method involves making the otherwise foreign device look like a very standard device so that the BIOS will then reserve memory for the device.
- the host system BIOS is called upon startup of the host or main system 200 .
- the BIOS 202 reserves and allocates system memory resources 206 for each device it sees on the bus 204 (for example, the PCI bus in the preferred embodiment).
- the BIOS 202 allocates system memory resources 206 by addressing each device 210 on the bus 204 and reading the contents of the class code register 208 of each of the devices 210 (boards, etc.) on the bus 204 .
- the memory 206 is located on a peripheral bus bridge 214 ( 25 in FIG. 1 ).
- Each device's class code register 208 includes a class code and sub-code that is predefined in the BIOS specification, and which tells the BIOS exactly what type of device is connected to the bus and how much and/or what type of memory to allocate for that device.
- the system and method of the present invention includes placing a “dummy” device 210 on the bus 204 .
- the dummy device 210 a will include a well known and standard class code/sub-class code in its class code register 208 a .
- the non-standard device 210 b such as a device with an embedded processor, etc., will not have a class code register 208 .
- An example of a well known device is an Ethernet card which every BIOS 202 will recognize.
- the BIOS 202 will then allocate a specified amount of memory 206 a to the particular device of interest 210 b (such as a nonstandard device) based on the class code of the dummy board 210 a . Subsequently, the driver 212 for the particular device 210 b of interest will determine the address range of the memory space 206 a allocated to the dummy device 210 a , and will divide and allocate that memory range to various elements (embedded processors, registers, FIFO's, etc.) on the device 210 b which will need to utilize the allocated memory space 206 a.
- elements embedded processors, registers, FIFO's, etc.
- the above described feature of the present invention provides for memory reservation by utilizing a dummy or surrogate device to reserve memory for a non-standard device, thus forcing the system BIOS to allocate memory to a desired device based on the class code of a dummy or surrogate device.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Input (AREA)
- Image Analysis (AREA)
- Bus Control (AREA)
Abstract
Description
- This application is a continuation of application Ser. No. 09/977,413, filed Oct. 15, 2001, which is a divisional of application Ser. No. 09/030,411, filed Feb. 25, 1998, which is a Continuation-in-Part of application Ser. No. 08/953,772, filed Oct. 17, 1997 (now U.S. Pat. No. 6,208,772) and claims the benefit of Provisional Application Ser. No. 60/066,339, filed Nov. 21, 1997. The entire teachings of the above applications are incorporated herein by reference.
- This invention relates to the field of flexible and modifiable processing hardware architecture and more particularly, to a processing hardware architecture that allows for multiple system configurations.
- The advent of the personal computer (PC) has enabled a variety of low cost processing systems such as image processing & machine vision system designs based on standardized hardware which take advantage of the technological innovation of the PC market.
- Four typical configurations of such PC based image processing and/or machine vision systems that are widely used today are highlighted below.
- In the simplest configuration of such as system, a frame grabber or camera interface board or system resides on the PC's peripheral bus and is used to acquire images from one or more cameras into the PC's memory where the images can be accessed and processed by the PC CPU. This will be referred to as the frame grabber or host processing configuration since the host CPU is solely responsible for all image processing operations.
- Another class of such systems uses a plug-in processor accelerator board to assist the PC CPU in performing some of the computationally expensive and extensive image processing operations. This will be referred to as the vision accelerator or accelerated host processing configuration.
- Yet another possible configuration involves a complete image processing or machine vision subsystem in the form of an expansion board plugged in the PC's peripheral bus. This board features and on-board CPU, often also coupled with dedicated image processing acceleration hardware. In this configuration, the embedded or target CPU completely off-loads all vision processing operations from the host PC CPU which can now be dedicated to user interface, control, or other tasks running on it concurrently with the image/vision processing tasks running on the vision processor. This multiprocessing configuration will be referred to as the embedded vision processing engine or target processing configuration.
- A final configuration uses the PC only as the programming and/or user interface environment for a standalone vision processing engine connected to it through a high speed serial or network connection. This configuration will be referred to as the standalone vision processing engine or standalone target processing configuration.
- Most recently, the PCI bus1 has enabled high bandwidth data transfers between a plug-in device such as an image acquisition or image processing board and the host PC, further enhancing the performance of all the above mentioned embedded system configurations.
1 PCI Local Bus Specification, Revision 2.1, Jun. 1, 1995
- The wide availability of PCI compatible components for the PC market makes it also attractive as a local bus to be used inside a processing subsystem such as the above mentioned image or vision processing subsystem configurations.
- Use of the PCI bus as a local bus is not without its drawbacks however. For example, the PCI bus was designed primarily for the PC market and as such, the topology and data flow is directed from a host CPU through a host bus bridge to a tree of peripheral buses connected through PCI to PCI bridges (herein referred to as peripheral bridges). The host CPU expects to be the only CPU in the system and also expects that its main memory is fixed in the system memory map. Any plug-in card, board or device with an embedded CPU has to allow its local memory to be mapped to avoid conflict with the host PC memory. Memory assignments may come from one or two sources: PCI BIOS or the host operating system (OS). Care must be taken when necessary to avoid system lockups by either hiding devices behind the peripheral bus bridges (where they are inaccessible by the host PC system), or by temporarily disconnecting them from the PCI bus until they are ready to accept bus transactions.
- A further drawback to using the PCI bus as a local bus inside PCI based systems is caused by a video graphics adapter (VGA), herein referred to as the display controller, and the discovery process used by the PCI BIOS and host Operating System (OS) to determine the system display controller. There are many different PCI BIOS manufacturers using different discovery algorithms some of which become confused by more than one display controller on the PCI bus. Also, PCI adapter card manufacturers who write drivers for their products sometimes introduce problems, e.g. when an expansion card has a peripheral bridge chip.
- This invention accordingly provides the following improvements over the current state of the art:
- 1. A flexible vision processing architecture that uses the PCI bus as the embedded processor local bus and which enables a variety of embedded and standalone vision system configurations to be implemented with either no or only minor hardware and software modifications.
- 2. Two different methods for hiding PCI devices that avoid conflicts with the host PC and allow for the embedded CPU to boot correctly.
- 3. Use of a peripheral bus register to reset the embedded CPU when the secondary PCI bus host bus bridge fails to respond, without affecting other secondary bus PCI devices and the host or primary CPU.
- 4. A method of loading the embedded CPU's local memory with diagnostics and Operating System code without the use of ROM or FLASH memory.
- These and other improvements over the prior art are realized by a reconfigurable vision or other processing system architecture, which is the subject matter of the present invention. The reconfigurable processing system architecture allows for the implementation of a variety of vision or other system configurations to be implemented on a single device, which, in one embodiment, is preferably a PCI bus add-in extension board with an attached digitizer daughter card attached and electrically connected thereto through a PCI Mezzanine connector, and which is plugged into a personal computer PCI expansion slot. The flexible and reconfigurable processing hardware architecture of the present invention uses the PCI bus as the embedded vision processor CPU's local bus, which not only allows for flexibility in vision system configuration but also allows PCI devices to be hidden from the host CPU to allow for proper system startup. The architecture further permits an embedded vision processing CPU to be re-booted when the secondary PCI bus host bus bridge fails to respond without affecting host CPU or other secondary PCI bus peripheral devices. Finally, the architecture of the present invention provides a method of loading an embedded vision system CPU's local memory with operating system and diagnostic code without the use of ROM or FLASH memory.
-
FIG. 1 is a the block diagram of an embedded processing engine configuration; -
FIG. 2 is a block diagram of a processing accelerator (with digitizer) configuration according to one embodiment of the present invention; -
FIG. 3 is a block diagram of a processing accelerator configured without a digitizer, according to another embodiment of the invention; -
FIG. 4 is a block diagram of a frame grabber configuration according to yet another embodiment of the invention; -
FIG. 5 is a block diagram of a standalone vision processing engine architecture according to one embodiment of the present invention; -
FIG. 6 is a schematic diagram showing a summary of some of the various different architectural configurations from the previous Figures; -
FIG. 7 is a flow chart showing the steps to accomplish the boot time reset; and -
FIG. 8 is a schematic diagram of a system for implementing the bus memory reservation according to another feature of the present invention. - The hardware described in this invention comprises, in the preferred embodiment, a PCI bus add-in
extension board 100 that includes a digitizer subsystem D embodied, for exemplary purposes, in a digitizer daughter card attached and electrically connected toextension board 100 through a PCI Mezzanine connector2 (pmc) 36; although such an implementation is not a limitation of the present invention.
2 Draft Standard Physical and Environmental Layers for PCI Mezzanine Cards: PMC, IEEE 1386/Draft 2.0, Apr. 4, 1995
- Although the present invention will be explained utilizing the PCI bus for exemplary purposes, this is not a limitation of the present invention. For example, the compact PCI bus specification which in one implementation is a 64 bit bus operating at 66 MHz and any other PCI bus specification to be specified in the future are considered to be within the scope of the present invention. In addition, any flexible architecture which utilizes a bus structure which makes two (2) devices look like they are connected together including a bus which allows for bus extensions with or without electrical buffering, and which bus and bus extension are designed to operate as a single bus, is considered to be within the scope of the present invention.
- On the
board 100 is a PCI toPCI bridge 3 25, which interfaces a host CPU PCIperipheral bus 27 to a secondary, vision processingsystem PCI bus 26 included on the PCI extension board.
3 See PCI to PCI bridge architecture specification Rev. 1.0
- The
extension board 100 also includes a processing accelerator subsystem A, implemented preferably as an ASIC (application specific integrated circuit) 20, a VGA (video graphics adapter) orsimilar display controller 33, and a system CPU subsystem C. The components of the system CPU subsystem C include an embeddedsystem CPU 16, which interfaces to the hostsystem PCI bus 27 via a CPUsubsystem CPU bus 15, ahost bus bridge 17, and the PCI toPCI bridge 25. Host system components which may be included in the subsystem include local DRAM (dynamic random access memory)system memory 22 andsystem peripherals 21 such as a DUART RS232 serial controller, NVRAM (non-volatile random access memory) with a real-time clock and a CPLD (complex programmable logic device) providing registers, CPU startup information and other board “glue” logic, as is well known in the art. Power is continually monitored by a CPU supervisory chip, which provides advanced warning to the CPU in the event of a power failure and further provides for manual board reset. - In the case wherein the present invention is implemented in a vision system, digitized video data is sent from the digitizer 12 (a
true data digitizer 12 in the case of an analog camera 14, or acamera interface 12 if the camera 14 is a digital camera) or other general purpose interface over the secondary, visionsystem PCI bus 26 tolocal DRAM 22 on the board or to the host PC'slocal display controller 35 having itsown memory 37. Thevision processing accelerator 20 “snoops” these transactions using snoop handshake, 21, thus loading theASIC memory processing accelerator 20, the data is sent to the embeddedvision system CPU 16 for further processing. Finally, the data may be displayed onlocal display 28 from thelocal display controller 33 or as an overlay in the host PC's display controller. - A plurality of boards can be mapped anywhere into PC memory within the host PC resource constraints and will not cause boot time conflicts with the PC hardware.
- The present invention includes the disclosed architecture which allows a wide variety of system variants to be implemented with minimal hardware and software incremental investment.
-
FIG. 1 shows the basic configuration for a vision processing engine system embedded in a PC as a PCI expansion board. By using the PCI bus as the local bus of the vision processing subsystem as well as the local bus of the host PC, the present invention takes advantage of widely available components and easily implements alternative vision system configurations through different combinations of the major functional groupings of the base architecture as will be explained below. - The main such functional groups shown in
FIG. 1 are the digitizer (also referred to as the frame grabber or camera interface) subsystem D, the vision CPU subsystem C, and the vision accelerator subsystem A. All these subsystems are connected to each other through the secondary, vision processingsystem PCI bus 26 which is itself connected to the PC's (Host CPU)PCI bus 27,host CPU 24 and associatedmemory 32 through a bus peripheral bus interface, which, in this embodiment is a PCI-to-PCI bus bridge 25 3.
3 PCI to PCI Bridge Architecture Specification, Rev. 1.0, Apr. 5, 1994.
- In the embodiment of such a vision system shown in
FIG. 1 ,image data 13 from multiple cameras 14 a-14 d can be processed by thevision accelerator 20, the embeddedvision system CPU 16, or by ahost CPU 24 in cases where the vision system is resident on the host CPU peripheral data bus (e.g. as an adapter or peripheral card). A vision system often includes alocal display 28 and serial and discrete input/output ports 30 to support real-time machine vision operations and intercommunications with other devices. - For maximum efficiency, the
digitizer 12 in this implementation packs multiple pixels (data samples) into a larger word to match the width of the vision processingsystem PCI bus 26. If the memory data bus 19 width and the vision processingsystem PCI bus 26 width are not the same, theprocessing accelerator 20 would reformat peripheral bus words to match the width of the memory data bus 19 or the vision processingsystem PCI bus 26. - The
digitizer 12, in connection with direct memory access (DMA)master controller 7, moves pixel data samples in high speed bursts into a portion of peripheral data bus address space. In the present invention, this may be one of theimage memories 18 a and/or 18 b, shared visionsystem CPU memory 22,host CPU memory 32,display controller memory 34, or hostdisplay controller memory 37. - A more detailed explanation of the operation of the embedded vision system including a processing accelerator A is provided in commonly owned patent application Ser. No. 08/953,772, which is incorporated herein by reference.
- To enhance the flexibility of this configuration further, the digitizer subsystem D is implemented as a mezzanine daughter card. Utilizing this implementation, a variety of different camera interface boards can be combined with the same vision
processing engine board 100. The connection to such a mezzanine card is through a PCI mezzanine connector (PMC) 36. -
FIG. 2 shows a cost reduced version of the embedded vision engine configuration ofFIG. 1 wherein the embeddedvision system CPU 16,host bus bridge 17,system memory 22,system peripherals 26 b and display controller are removed to create the accelerated host configuration mentioned earlier. - In the embodiment of
FIG. 2 , the vision processing system comprises a digitizer subsystem D, which includes substantially the same components discussed above with respect to the-digitizer subsystem ofFIG. 1 . (The common components of the two digitizer subsystems are identified using the same reference numerals.) The second component of the vision processing system ofFIG. 2 is the vision accelerator subsystem A, which, like the digitizer subsystem D, is substantially identical to the processing accelerator subsystem A ofFIG. 1 and common components are indicated using the same reference numerals. This embodiment can be implemented using a plug-in expansion card in much the same manner as the embodiment ofFIG. 1 . However, the expansion card would not include the components of the vision CPU subsystem C (ofFIG. 1 ). In this embodiment, the,host CPU 24 is tasked with running the vision subsystem application. However, the vision accelerator subsystem would still be available with itsprocessing accelerator ASIC 20, which would allow digitized video information to be pre-processed before it is routed to thehost CPU 24 for further processing. -
FIG. 3 shows a further cost-reduced variation of the above-mentioned processing accelerator configuration. This configuration incorporates only the processing accelerator subsystem A without a digitizer subsystem. Here, images are acquired through a separate frame grabber board (not shown). As in the configuration ofFIG. 2 , thehost PC CPU 24 runs the vision application. However, the visionprocessing accelerator ASIC 20 is still available to accelerate vision computations. - As
FIG. 4 further shows, a frame grabber (digitizer) D′, which can be built from the mezzanine card components by changing the PCI mezzanine connector (36 ofFIG. 1 ) to a standard PCI edge connector (not shown), may interface directly to the host CPU PCIperipheral bus 27. This further allows for the development of software drivers from existing software components. - Turning now to
FIG. 5 , a fifth embodiment of the invention is shown. In this embodiment, an Ethernet controller 25 c or any other communications means such as PPP (TCPIP protocol over a serial line), can be attached to the vision systemperipheral bus 26 in place of the PCI-to-PCI bus bridge 25 ofFIG. 1 , so that the vision processor acts as a standalone vision processor. As can be seen inFIG. 5 , the standalone vision processor configuration includes most of the same components described above with respect to the vision system ofFIG. 1 . - Other configurations can be envisioned with different functional groupings of the basic subsystems highlighted in
FIG. 1 , including for example, but not limited to, incorporating a camera in the same package as the vision processing engine to form a “smart camera” configuration. - A summary of the preceding Figures is shown in
FIGS. 6 a-6 e, wherein block ‘C’ represents the Embedded CPU Subsystem including the CPU, host bus bridge, system memory, peripherals, Ethernet controller and display controller; block ‘D’ represents the Digitizer and Field I/O mezzanine card (100 d having a PCI or other system buscompatible edge connector 150 such as a PCI mezzanine connector); and block ‘A’ represents the processing accelerator and its captive memories. “H” represents a host computer, which is accessed via an Ethernet or PPP connection. - The key challenges in making this architecture work are highlighted in the following sections.
- Up to 21 PCI devices may be addressed on a PCI bus. When devices lie behind a peripheral bridge on its secondary bus, the bridge architecture specification will allow up to 16 devices to be addressed. Secondary bus addressing is implemented by connecting the device IDSEL line to a PCI address line in the range AD [31:16]. When a configuration cycle is issued for a device on the same bus as the target, up to 21 devices may be addressed on AD [31:11], the remaining lines being used to identify configuration cycle type, configuration register number and device function number. This means that a device on the secondary bus (side) of the
peripheral bus bridge 25 and connected to AD [15:11] is hidden from the primary side of theperipheral bus bridge 25, but not from the embedded CPU on the secondary PCI bus. - The display controller that is used as a local (secondary) display device confuses both the PCI BIOS (Basic Input Output System) and the installed host PC's display controller drivers as to which display device should be used as the system display device. Hiding this local display device behind the PCI bridge (by connecting its IDSEL line to a PCI address line in the range AD [15:11]) means that the display device is only addressable for PCI configuration cycles by the embedded CPU.
- Although this method provides a way to initialize a private device behind a peripheral bridge, the device is always visible in the final system memory map if the peripheral bridge's memory window encompasses the device's assigned memory region.
- Another method to hide PCI devices addresses power-on issues (e.g. when the PCI BIOS tries to interrogate the host bus bridge before its initialization sequence is complete it could cause the host PC to “hang” during boot).
- When a PCI device has multiple clock domains the other clock(s) may be supplied from a source that has a long startup latency for a variety of reasons. The device may also require all clocks to be operational before it can reset its internal state machines. If this delay time is greater than the time that the PC needs before it starts executing its BIOS code, there is the potential for deadlock. Here, a state machine (its operation shown in
FIG. 7 ) is used to control the reset release and the PCI device's IDSEL connection sequencing, to ensure correct operation—effectively disconnecting the device from the PCI bus until it is ready to accept bus transactions. - In state S0,
step 110, thestate machine 100 asserts cold CPU reset, asserts host bus bridge reset, disables IDSEL to the host bus bridge, asserts warm CPU reset and resets an 8-bit counter to a count value of 0 (counter reset). In state S1,step 120, which is reached when power reaches a sufficient level or manual reset is released, the state machine continues to assert cold CPU reset and host bus bridge reset. It releases the counter reset to allow the counter to increment, and continues to disable IDSEL and assert warm CPU reset. Progression to state S2,step 130 will happen when the counter value reaches 255 (256 clock cycles after S1), and the state machine de-asserts cold CPU reset. However, host bus bridge reset remains asserted as does warm CPU reset. In addition, IDSEL remains disabled. Thus, the host CPU can load its mode information and start its system clocks. - In state S3,
step 140, the state machine continues to de-assert cold CPU reset. It also de-asserts host bus bridge reset, thus allowing the bridge to complete its internal initialization. IDSEL remains disabled and warm CPU reset remains asserted. Moving on to state S4,step 150, IDSEL is enabled, thus allowing host bus bridge to become visible on the secondary system (vision system in this implementation) and visible to the host PC. (Cold CPU reset and host bus bridge reset remain de-asserted and warm CPU reset remains asserted.) - Progression from state S4 to state S5 will generally not occur immediately, the average wait time being 128 clock cycles. The 8 bit counter is enabled in all states except state S0, and will continually count with a modulo of 256. There is a minimum wait of one cycle possible which is enough to perform a soft reset on the CPU.
- Finally, in state S5,
step 160, warm CPU reset is deasserted under software control by deasserting a “halt” register bit with the CPU. Thus, the embedded (vision) system CPU is allowed to boot. This state progression thus allows two CPU's and multiple, potentially conflicting peripheral components to be sequentially initialized without causing system hang-ups. - In summary, the Boot
Time State Machine 100 performs three functions: - 1. It waits for all the clocks that are needed by the device to be active;
- 2. It asserts device reset until after the clocks are present; and
- 3. It holds IDSEL disabled until a programmable number of PCI clock cycles after reset is deasserted.
- The first feature above solves the problem that the embedded CPU must provide a synchronous clock to the host bus bridge which operates at a different frequency from the oscillator that supplies the embedded CPU. Therefore, the CPU frequency generator must supply the host bus bridge clock. This supplied clock is started only after the embedded CPU has loaded it's mode information from the complex programmable logic device CPLD. Reset must be deasserted only after the clock from the CPU is present so that the host bus bridge can correctly initialize its internal state. PCI accesses should not be responded to until enough PCI clock cycles have passed from reset deassertion to ensure that the reset completes correctly.
- This solution is also equally applicable to a PCI device on the primary or secondary side of a peripheral bridge and anywhere in the PCI bus hierarchy.
- Although this method provides a way to initialize a private device behind a peripheral bridge, the device is always visible in the final system memory map if the peripheral bridge memory window encompasses the device's assigned memory region.
- When the host bus bridge device locks up the secondary PCI bus, the embedded CPU and its devices are inaccessible from the primary PCI bus, including any device registers that can assert a soft reset to the CPU.
- A back-door signal (26 d of
FIG. 1 ) was created from the peripheral bridge to a system peripheral that ensures resets can be asserted to recover the system. While this is useful primarily for debugging, its use in the driver ensures that no problems occur during driver loading. The signal is attached to the peripheral bridge's general purpose input/output (GPIO) port which is addressable from configuration space on the primary bus. - An embedded CPU is usually tested and booted by running code that is present in an on-board ROM or FLASH memory because there is no other way to load this code into the embedded CPU's memory.
- With this architecture, code can be loaded over the PCI bus from any source, including an Ethernet device or a host PC. This allows the ROM or FLASH memory to be removed from the board which reduces cost and allows easy field updates by disk or Internet/Intranet.
- An additional feature of the present invention facilitates and allows for the use of a non-standard or non-recognized PCI bus connected device such as, for example, a vision system board, embedded CPU or other similar device. When the main system BIOS (the PC (personal computer) boots, the BIOS scans the bus for devices connected to the bus, and allocates system memory for each device. If the BIOS sees a device that it does not recognize, the BIOS ignores the device and does not allocate memory for that particular device.
- Accordingly, the present invention features a system and method for reserving memory in such a situation; such a system and method being completely independent of the type of BIOS and the type of device plugged into the PCI or other bus. The system and method involves making the otherwise foreign device look like a very standard device so that the BIOS will then reserve memory for the device.
- For example, in the case of a host or
main processing system 200,FIG. 8 , such as a PC, the host system BIOS is called upon startup of the host ormain system 200. TheBIOS 202 reserves and allocatessystem memory resources 206 for each device it sees on the bus 204 (for example, the PCI bus in the preferred embodiment). TheBIOS 202 allocatessystem memory resources 206 by addressing eachdevice 210 on thebus 204 and reading the contents of theclass code register 208 of each of the devices 210 (boards, etc.) on thebus 204. In the preferred embodiment described herein, thememory 206 is located on a peripheral bus bridge 214 (25 inFIG. 1 ). Each device'sclass code register 208 includes a class code and sub-code that is predefined in the BIOS specification, and which tells the BIOS exactly what type of device is connected to the bus and how much and/or what type of memory to allocate for that device. - Accordingly, the system and method of the present invention includes placing a “dummy”
device 210 on thebus 204. Thedummy device 210 a will include a well known and standard class code/sub-class code in its class code register 208 a. Thenon-standard device 210 b, such as a device with an embedded processor, etc., will not have aclass code register 208. An example of a well known device is an Ethernet card which everyBIOS 202 will recognize. - The
BIOS 202 will then allocate a specified amount ofmemory 206 a to the particular device ofinterest 210 b (such as a nonstandard device) based on the class code of thedummy board 210 a. Subsequently, the driver 212 for theparticular device 210 b of interest will determine the address range of thememory space 206 a allocated to thedummy device 210 a, and will divide and allocate that memory range to various elements (embedded processors, registers, FIFO's, etc.) on thedevice 210 b which will need to utilize the allocatedmemory space 206 a. - In this manner, the above described feature of the present invention provides for memory reservation by utilizing a dummy or surrogate device to reserve memory for a non-standard device, thus forcing the system BIOS to allocate memory to a desired device based on the class code of a dummy or surrogate device.
- Modifications and substitutions by one of ordinary skill in the art are considered to be within the scope of the present invention which is not to be limited except by the claims which follow.
Claims (13)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/404,193 US20060190656A1 (en) | 1997-10-17 | 2006-04-14 | Flexible processing hardware architecture |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/953,772 US6208772B1 (en) | 1997-10-17 | 1997-10-17 | Data processing system for logically adjacent data samples such as image data in a machine vision system |
US09/030,411 US6308234B1 (en) | 1997-10-17 | 1998-02-25 | Flexible processing hardware architecture |
US09/977,413 US7062578B2 (en) | 1997-10-17 | 2001-10-15 | Flexible processing hardware architecture |
US11/404,193 US20060190656A1 (en) | 1997-10-17 | 2006-04-14 | Flexible processing hardware architecture |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/977,413 Division US7062578B2 (en) | 1997-10-17 | 2001-10-15 | Flexible processing hardware architecture |
Publications (1)
Publication Number | Publication Date |
---|---|
US20060190656A1 true US20060190656A1 (en) | 2006-08-24 |
Family
ID=25494513
Family Applications (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US08/953,772 Expired - Lifetime US6208772B1 (en) | 1997-10-17 | 1997-10-17 | Data processing system for logically adjacent data samples such as image data in a machine vision system |
US09/025,937 Expired - Lifetime US6041148A (en) | 1997-10-17 | 1998-02-19 | System and method for extracting image data |
US09/025,938 Expired - Lifetime US5977994A (en) | 1997-10-17 | 1998-02-19 | Data resampler for data processing system for logically adjacent data samples |
US11/404,193 Abandoned US20060190656A1 (en) | 1997-10-17 | 2006-04-14 | Flexible processing hardware architecture |
Family Applications Before (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US08/953,772 Expired - Lifetime US6208772B1 (en) | 1997-10-17 | 1997-10-17 | Data processing system for logically adjacent data samples such as image data in a machine vision system |
US09/025,937 Expired - Lifetime US6041148A (en) | 1997-10-17 | 1998-02-19 | System and method for extracting image data |
US09/025,938 Expired - Lifetime US5977994A (en) | 1997-10-17 | 1998-02-19 | Data resampler for data processing system for logically adjacent data samples |
Country Status (7)
Country | Link |
---|---|
US (4) | US6208772B1 (en) |
EP (1) | EP1031108A4 (en) |
JP (1) | JP2003517649A (en) |
KR (1) | KR20010031192A (en) |
AU (1) | AU747283B2 (en) |
CA (1) | CA2308328A1 (en) |
WO (1) | WO1999021126A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106126453A (en) * | 2016-06-13 | 2016-11-16 | 浪潮电子信息产业股份有限公司 | Method for implementing CPU with external interface |
US11096012B2 (en) * | 2019-05-29 | 2021-08-17 | Texas Instruments Incorporated | Integrated Wi-Fi location |
Families Citing this family (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6459439B1 (en) * | 1998-03-09 | 2002-10-01 | Macromedia, Inc. | Reshaping of paths without respect to control points |
US6160423A (en) * | 1998-03-16 | 2000-12-12 | Jazio, Inc. | High speed source synchronous signaling for interfacing VLSI CMOS circuits to transmission lines |
JP2001243460A (en) * | 2000-02-29 | 2001-09-07 | Fuji Photo Film Co Ltd | Image processor and image processing program storage medium |
AUPQ668500A0 (en) * | 2000-04-04 | 2000-05-04 | Canon Kabushiki Kaisha | Accessing items of information |
DE60120474T2 (en) * | 2000-12-18 | 2007-01-04 | Lightspace Technologies, Inc. | GRINDING OF THREE-DIMENSIONAL PICTURES |
US6965606B2 (en) * | 2001-01-26 | 2005-11-15 | Exar Corporation | Method and apparatus for byte rotation |
KR100698549B1 (en) * | 2001-06-04 | 2007-03-21 | 에스케이케미칼주식회사 | Culture medium of microorganism for treatmenting waste water |
US6620246B2 (en) | 2001-06-14 | 2003-09-16 | Nylok Corporation | Process controller for coating fasteners |
JP3703754B2 (en) * | 2001-10-23 | 2005-10-05 | 富士通株式会社 | Drawing apparatus and information processing apparatus |
US20030137590A1 (en) * | 2002-01-18 | 2003-07-24 | Barnes Danny S. | Machine vision system with auxiliary video input |
US6871409B2 (en) | 2002-12-18 | 2005-03-29 | Snap-On Incorporated | Gradient calculating camera board |
US20040243767A1 (en) * | 2003-06-02 | 2004-12-02 | Cierniak Michal J. | Method and apparatus for prefetching based upon type identifier tags |
JP2006157580A (en) * | 2004-11-30 | 2006-06-15 | Ricoh Co Ltd | Image processor, image forming apparatus, image processing method, computer program, and recording medium |
US7855783B2 (en) * | 2007-09-18 | 2010-12-21 | Snap-On Incorporated | Integrated circuit image sensor for wheel alignment systems |
US9390661B2 (en) * | 2009-09-15 | 2016-07-12 | E Ink California, Llc | Display controller system |
US8130229B2 (en) | 2009-11-17 | 2012-03-06 | Analog Devices, Inc. | Methods and apparatus for image processing at pixel rate |
US20130027416A1 (en) * | 2011-07-25 | 2013-01-31 | Karthikeyan Vaithianathan | Gather method and apparatus for media processing accelerators |
US8488882B1 (en) * | 2011-08-10 | 2013-07-16 | Google Inc. | Non-linear transformation of images in web browsers |
JP6385077B2 (en) * | 2014-03-05 | 2018-09-05 | ルネサスエレクトロニクス株式会社 | Semiconductor device |
US10262624B2 (en) * | 2014-12-29 | 2019-04-16 | Synaptics Incorporated | Separating a compressed stream into multiple streams |
WO2019173622A1 (en) | 2018-03-07 | 2019-09-12 | Anokiwave, Inc. | Phased array with low-latency control interface |
CN109191374B (en) * | 2018-10-10 | 2020-05-08 | 京东方科技集团股份有限公司 | Distortion parameter measuring method, device and system |
US11205858B1 (en) | 2018-10-16 | 2021-12-21 | Anokiwave, Inc. | Element-level self-calculation of phased array vectors using direct calculation |
US10985819B1 (en) * | 2018-10-16 | 2021-04-20 | Anokiwave, Inc. | Element-level self-calculation of phased array vectors using interpolation |
TWI830363B (en) * | 2022-05-19 | 2024-01-21 | 鈺立微電子股份有限公司 | Sensing device for providing three dimensional information |
Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5564114A (en) * | 1995-01-09 | 1996-10-08 | Cirrus Logic Inc. | Method and an arrangement for handshaking on a bus to transfer information between devices in a computer system |
US5608876A (en) * | 1995-05-22 | 1997-03-04 | International Business Machines Corporation | Add-in board with enable-disable expansion ROM for PCI bus computers |
US5761461A (en) * | 1996-12-13 | 1998-06-02 | International Business Machines Corporation | Method and system for preventing peripheral component interconnect (PCI) peer-to-peer access across multiple PCI host bridges within a data processing system |
US5764968A (en) * | 1995-08-21 | 1998-06-09 | Kabushiki Kaisha Toshiba | Clock supply permission/inhibition control system |
US5784576A (en) * | 1996-10-31 | 1998-07-21 | International Business Machines Corp. | Method and apparatus for adding and removing components of a data processing system without powering down |
US5884027A (en) * | 1995-06-15 | 1999-03-16 | Intel Corporation | Architecture for an I/O processor that integrates a PCI to PCI bridge |
US5889480A (en) * | 1996-10-18 | 1999-03-30 | Samsung Electronics Co., Ltd. | Full duplex serial codec interface with DMA |
US5933614A (en) * | 1996-12-31 | 1999-08-03 | Compaq Computer Corporation | Isolation of PCI and EISA masters by masking control and interrupt lines |
US5937173A (en) * | 1997-06-12 | 1999-08-10 | Compaq Computer Corp. | Dual purpose computer bridge interface for accelerated graphics port or registered peripheral component interconnect devices |
US5935233A (en) * | 1997-05-21 | 1999-08-10 | Micron Electronics, Inc. | Computer system with a switch interconnector for computer devices |
US5969750A (en) * | 1996-09-04 | 1999-10-19 | Winbcnd Electronics Corporation | Moving picture camera with universal serial bus interface |
US5978493A (en) * | 1996-12-16 | 1999-11-02 | International Business Machines Corporation | Identification bracelet for child and guardian matching |
US5987590A (en) * | 1996-04-02 | 1999-11-16 | Texas Instruments Incorporated | PC circuits, systems and methods |
US6047349A (en) * | 1997-06-11 | 2000-04-04 | Micron Electronics, Inc. | System for communicating through a computer system bus bridge |
US6094699A (en) * | 1998-02-13 | 2000-07-25 | Mylex Corporation | Apparatus and method for coupling devices to a PCI-to-PCI bridge in an intelligent I/O controller |
US6118886A (en) * | 1993-03-30 | 2000-09-12 | The United States Of America As Represented By The United States Department Of Energy | Automatic target recognition apparatus and method |
US6125418A (en) * | 1996-11-27 | 2000-09-26 | Compaq Computer Corporation | Method and apparatus for enabling a computer user to convert a computer system to an intelligent I/O system |
US6134579A (en) * | 1997-08-15 | 2000-10-17 | Compaq Computer Corporation | Semaphore in system I/O space |
US6985990B2 (en) * | 2002-03-29 | 2006-01-10 | International Business Machines Corporation | System and method for implementing private devices on a secondary peripheral component interface |
US7082487B2 (en) * | 2002-02-20 | 2006-07-25 | Spectrum Signal Processing, Inc. | Multiple configurable I/O common mezzanine cards |
Family Cites Families (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4484346A (en) * | 1980-08-15 | 1984-11-20 | Sternberg Stanley R | Neighborhood transformation logic circuitry for an image analyzer system |
US4554593A (en) * | 1981-01-02 | 1985-11-19 | International Business Machines Corporation | Universal thresholder/discriminator |
US4577344A (en) | 1983-01-17 | 1986-03-18 | Automatix Incorporated | Vision system |
JPH0778825B2 (en) * | 1983-02-09 | 1995-08-23 | 株式会社日立製作所 | Image processing processor |
US4541114A (en) * | 1983-05-05 | 1985-09-10 | Research Environmental/Institute of Michigan | Routing techniques using serial neighborhood image analyzing system |
US4742552A (en) * | 1983-09-27 | 1988-05-03 | The Boeing Company | Vector image processing system |
US4581762A (en) | 1984-01-19 | 1986-04-08 | Itran Corporation | Vision inspection system |
US4648119A (en) * | 1985-03-18 | 1987-03-03 | Tektronix, Inc. | Method and apparatus for forming 3×3 pixel arrays and for performing programmable pattern contingent modifications of those arrays |
US4790026A (en) * | 1985-12-31 | 1988-12-06 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Programmable pipelined image processor |
US5717440A (en) * | 1986-10-06 | 1998-02-10 | Hitachi, Ltd. | Graphic processing having apparatus for outputting FIFO vacant information |
US4972359A (en) | 1987-04-03 | 1990-11-20 | Cognex Corporation | Digital image processing system |
US5129092A (en) | 1987-06-01 | 1992-07-07 | Applied Intelligent Systems,Inc. | Linear chain of parallel processors and method of using same |
US5146592A (en) * | 1987-09-14 | 1992-09-08 | Visual Information Technologies, Inc. | High speed image processing computer with overlapping windows-div |
US5384912A (en) * | 1987-10-30 | 1995-01-24 | New Microtime Inc. | Real time video image processing system |
US5268856A (en) | 1988-06-06 | 1993-12-07 | Applied Intelligent Systems, Inc. | Bit serial floating point parallel processing system and method |
US4967378A (en) * | 1988-09-13 | 1990-10-30 | Microsoft Corporation | Method and system for displaying a monochrome bitmap on a color display |
US4974261A (en) * | 1988-11-15 | 1990-11-27 | Matsushita Electric Works, Ltd. | Optical surface inspection method |
NL8803112A (en) | 1988-12-19 | 1990-07-16 | Elbicon Nv | METHOD AND APPARATUS FOR SORTING A FLOW OF ARTICLES DEPENDING ON OPTICAL PROPERTIES OF THE ARTICLES. |
US4972495A (en) * | 1988-12-21 | 1990-11-20 | General Electric Company | Feature extraction processor |
US5144683A (en) * | 1989-04-28 | 1992-09-01 | Hitachi, Ltd. | Character recognition equipment |
JPH0486961A (en) * | 1990-07-31 | 1992-03-19 | Toshiba Corp | Device and method for generating paint-out pattern |
US5115309A (en) | 1990-09-10 | 1992-05-19 | At&T Bell Laboratories | Method and apparatus for dynamic channel bandwidth allocation among multiple parallel video coders |
JPH087715B2 (en) * | 1990-11-15 | 1996-01-29 | インターナショナル・ビジネス・マシーンズ・コーポレイション | Data processing device and access control method |
US5341468A (en) * | 1991-01-28 | 1994-08-23 | Ricoh Company, Ltd. | Image processor |
JPH0568243A (en) | 1991-09-09 | 1993-03-19 | Hitachi Ltd | Variable length coding controlling system |
US5173951A (en) * | 1991-10-10 | 1992-12-22 | Unisys Corporation | Word oriented image smoothing apparatus and method |
US5315388A (en) | 1991-11-19 | 1994-05-24 | General Instrument Corporation | Multiple serial access memory for use in feedback systems such as motion compensated television |
US5216503A (en) | 1991-12-24 | 1993-06-01 | General Instrument Corporation | Statistical multiplexer for a multichannel image compression system |
US5657403A (en) | 1992-06-01 | 1997-08-12 | Cognex Corporation | Vision coprocessing |
US5623624A (en) * | 1993-02-01 | 1997-04-22 | Micron Technology, Inc. | Memory control architecture for high speed transfer options |
US5550972A (en) * | 1993-06-30 | 1996-08-27 | Microsoft Corporation | Method and apparatus for efficient transfer of data to memory |
US5583954A (en) | 1994-03-01 | 1996-12-10 | Cognex Corporation | Methods and apparatus for fast correlation |
US5526050A (en) | 1994-03-31 | 1996-06-11 | Cognex Corporation | Methods and apparatus for concurrently acquiring video data from multiple video data sources |
US5602937A (en) | 1994-06-01 | 1997-02-11 | Cognex Corporation | Methods and apparatus for machine vision high accuracy searching |
US5557734A (en) | 1994-06-17 | 1996-09-17 | Applied Intelligent Systems, Inc. | Cache burst architecture for parallel processing, such as for image processing |
US5536559A (en) * | 1994-11-22 | 1996-07-16 | Wisconsin Alumni Research Foundation | Stress-free mount for imaging mask |
US5706483A (en) * | 1994-12-13 | 1998-01-06 | Microsoft Corporation | Run-time code compiler for data block transfer |
US5784047A (en) * | 1995-04-28 | 1998-07-21 | Intel Corporation | Method and apparatus for a display scaler |
US5835160A (en) * | 1995-09-13 | 1998-11-10 | Oak Technology, Inc. | Sampling rate conversion using digital differential analyzers |
US6084600A (en) * | 1996-03-15 | 2000-07-04 | Micron Technology, Inc. | Method and apparatus for high-speed block transfer of compressed and word-aligned bitmaps |
-
1997
- 1997-10-17 US US08/953,772 patent/US6208772B1/en not_active Expired - Lifetime
-
1998
- 1998-02-19 US US09/025,937 patent/US6041148A/en not_active Expired - Lifetime
- 1998-02-19 US US09/025,938 patent/US5977994A/en not_active Expired - Lifetime
- 1998-05-08 WO PCT/US1998/009445 patent/WO1999021126A1/en not_active Application Discontinuation
- 1998-05-08 CA CA002308328A patent/CA2308328A1/en not_active Abandoned
- 1998-05-08 KR KR1020007004135A patent/KR20010031192A/en not_active Application Discontinuation
- 1998-05-08 EP EP98921067A patent/EP1031108A4/en not_active Withdrawn
- 1998-05-08 JP JP2000517374A patent/JP2003517649A/en active Pending
- 1998-05-08 AU AU73752/98A patent/AU747283B2/en not_active Ceased
-
2006
- 2006-04-14 US US11/404,193 patent/US20060190656A1/en not_active Abandoned
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6118886A (en) * | 1993-03-30 | 2000-09-12 | The United States Of America As Represented By The United States Department Of Energy | Automatic target recognition apparatus and method |
US5564114A (en) * | 1995-01-09 | 1996-10-08 | Cirrus Logic Inc. | Method and an arrangement for handshaking on a bus to transfer information between devices in a computer system |
US5608876A (en) * | 1995-05-22 | 1997-03-04 | International Business Machines Corporation | Add-in board with enable-disable expansion ROM for PCI bus computers |
US5884027A (en) * | 1995-06-15 | 1999-03-16 | Intel Corporation | Architecture for an I/O processor that integrates a PCI to PCI bridge |
US5764968A (en) * | 1995-08-21 | 1998-06-09 | Kabushiki Kaisha Toshiba | Clock supply permission/inhibition control system |
US5987590A (en) * | 1996-04-02 | 1999-11-16 | Texas Instruments Incorporated | PC circuits, systems and methods |
US5969750A (en) * | 1996-09-04 | 1999-10-19 | Winbcnd Electronics Corporation | Moving picture camera with universal serial bus interface |
US5889480A (en) * | 1996-10-18 | 1999-03-30 | Samsung Electronics Co., Ltd. | Full duplex serial codec interface with DMA |
US5784576A (en) * | 1996-10-31 | 1998-07-21 | International Business Machines Corp. | Method and apparatus for adding and removing components of a data processing system without powering down |
US6125418A (en) * | 1996-11-27 | 2000-09-26 | Compaq Computer Corporation | Method and apparatus for enabling a computer user to convert a computer system to an intelligent I/O system |
US5761461A (en) * | 1996-12-13 | 1998-06-02 | International Business Machines Corporation | Method and system for preventing peripheral component interconnect (PCI) peer-to-peer access across multiple PCI host bridges within a data processing system |
US5978493A (en) * | 1996-12-16 | 1999-11-02 | International Business Machines Corporation | Identification bracelet for child and guardian matching |
US5933614A (en) * | 1996-12-31 | 1999-08-03 | Compaq Computer Corporation | Isolation of PCI and EISA masters by masking control and interrupt lines |
US5935233A (en) * | 1997-05-21 | 1999-08-10 | Micron Electronics, Inc. | Computer system with a switch interconnector for computer devices |
US6047349A (en) * | 1997-06-11 | 2000-04-04 | Micron Electronics, Inc. | System for communicating through a computer system bus bridge |
US5937173A (en) * | 1997-06-12 | 1999-08-10 | Compaq Computer Corp. | Dual purpose computer bridge interface for accelerated graphics port or registered peripheral component interconnect devices |
US6134579A (en) * | 1997-08-15 | 2000-10-17 | Compaq Computer Corporation | Semaphore in system I/O space |
US6094699A (en) * | 1998-02-13 | 2000-07-25 | Mylex Corporation | Apparatus and method for coupling devices to a PCI-to-PCI bridge in an intelligent I/O controller |
US7082487B2 (en) * | 2002-02-20 | 2006-07-25 | Spectrum Signal Processing, Inc. | Multiple configurable I/O common mezzanine cards |
US6985990B2 (en) * | 2002-03-29 | 2006-01-10 | International Business Machines Corporation | System and method for implementing private devices on a secondary peripheral component interface |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106126453A (en) * | 2016-06-13 | 2016-11-16 | 浪潮电子信息产业股份有限公司 | Method for implementing CPU with external interface |
US11096012B2 (en) * | 2019-05-29 | 2021-08-17 | Texas Instruments Incorporated | Integrated Wi-Fi location |
US20210337361A1 (en) * | 2019-05-29 | 2021-10-28 | Texas Instruments Incorporated | Integrated wi-fi location |
US11825381B2 (en) * | 2019-05-29 | 2023-11-21 | Texas Instruments Incorporated | Integrated Wi-Fi location |
Also Published As
Publication number | Publication date |
---|---|
US6041148A (en) | 2000-03-21 |
EP1031108A4 (en) | 2001-01-24 |
CA2308328A1 (en) | 1999-04-29 |
US5977994A (en) | 1999-11-02 |
US6208772B1 (en) | 2001-03-27 |
AU7375298A (en) | 1999-05-10 |
EP1031108A1 (en) | 2000-08-30 |
WO1999021126A1 (en) | 1999-04-29 |
JP2003517649A (en) | 2003-05-27 |
AU747283B2 (en) | 2002-05-09 |
KR20010031192A (en) | 2001-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7062578B2 (en) | Flexible processing hardware architecture | |
US20060190656A1 (en) | Flexible processing hardware architecture | |
KR100262677B1 (en) | ADD-IN Board With Enable/Disable Expansion ROM for PCI BUS Computer | |
US5872998A (en) | System using a primary bridge to recapture shared portion of a peripheral memory of a peripheral device to provide plug and play capability | |
US7024510B2 (en) | Supporting a host-to-input/output (I/O) bridge | |
EP1252569B1 (en) | Virtual rom for device enumeration | |
US6035355A (en) | PCI system and adapter requirements following reset | |
US5911084A (en) | System and method for accessing peripheral devices on a non-functional controller | |
US6085273A (en) | Multi-processor computer system having memory space accessible to multiple processors | |
JPH06348642A (en) | Method and apparatus for initialization of multiple bus network | |
US20040117743A1 (en) | Heterogeneous multi-processor reference design | |
US7100088B2 (en) | Computer system equipped with a BIOS debugging card | |
US6297817B1 (en) | Computer system with multiple monitor control signal synchronization apparatus and method | |
US6216196B1 (en) | System and method for multiple device drivers to arbitrate for a single device | |
US6241400B1 (en) | Configuration logic within a PCI compliant bus interface unit which can be selectively disconnected from a clocking source to conserve power | |
US5859987A (en) | Method and apparatus for providing multiple configuration reset modes for an intelligent bridge | |
EP0581698A1 (en) | Programmable microprocessor booting technique | |
JPH05257657A (en) | Power-on time sequence device | |
US5894563A (en) | Method and apparatus for providing a PCI bridge between multiple PCI environments | |
US6691224B1 (en) | Computer system for accessing initialization data and method therefor | |
US6018781A (en) | Work station having simultaneous access to registers contained in two different interfaces | |
US20040068596A1 (en) | Integrated PCI interface card and bus system thereof | |
JP2001034571A (en) | Information processor | |
JP2003271573A (en) | Multiprocessor, multiprocessor core and control method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: ACUITY CIMATRIX, INC., NEW HAMPSHIRE Free format text: CHANGE OF NAME;ASSIGNOR:ROBOTIC VISION SYSTEMS, INC.;REEL/FRAME:022351/0171 Effective date: 20050328 Owner name: SIEMENS ENERGY AND AUTOMATION, INC., NEW JERSEY Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:ACUITY CIMATRIX, INC.;REEL/FRAME:022351/0099 Effective date: 20051003 Owner name: ROBOTIC VISON SYSTEMS, INC., MASSACHUSETTS Free format text: MERGER;ASSIGNOR:ACUITY IMAGING LLC;REEL/FRAME:022351/0038 Effective date: 20000929 Owner name: ACUITY IMAGING, LLC, NEW HAMPSHIRE Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:DAVIES, DAVID C.;GREENBERG, MICHAEL P.;WILT, MICHAEL J.;AND OTHERS;REEL/FRAME:022350/0987;SIGNING DATES FROM 19980220 TO 19980223 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |
|
AS | Assignment |
Owner name: MICROSCAN SYSTEMS, INC., WASHINGTON Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SIEMENS AKTIENGESELLSCHAFT;REEL/FRAME:023445/0150 Effective date: 20090604 Owner name: SIEMENS AKTIENGESELLSCHAFT, GERMANY Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SIEMENS ENERGY & AUTOMATION, INC.;REEL/FRAME:023444/0945 Effective date: 20090528 |